# ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

arXiv: https://arxiv.org/abs/2410.02052 · HTML: https://mlsanity.com/paper/2410.02052/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://mlsanity.com/paper/2409.03215/) (2024)
- [SteP: Stacked LLM Policies for Web Actions](https://mlsanity.com/paper/2310.03720/) (2023)
- [Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning](https://mlsanity.com/paper/2305.13660/) (2023)
- [AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning](https://mlsanity.com/paper/2402.15506/) (2024)
- [Hierarchical Prompting Assists Large Language Model on Web Navigation](https://mlsanity.com/paper/2305.14257/) (2023)
- [Teaching Language Models to Self-Improve through Interactive Demonstrations](https://mlsanity.com/paper/2310.13522/) (2023)

## Built on by (most cited first, 30 of 62)

- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://mlsanity.com/paper/2501.04682/) (2025)
- [InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://mlsanity.com/paper/2501.04575/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model](https://mlsanity.com/paper/2504.21024/) (2025)
- [OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization](https://mlsanity.com/paper/2410.19609/) (2024)
- [Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2502.16707/) (2025)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction](https://mlsanity.com/paper/2506.07976/) (2025)
- [Visual Test-time Scaling for GUI Agent Grounding](https://mlsanity.com/paper/2505.00684/) (2025)
- [BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism](https://mlsanity.com/paper/2505.20660/) (2025)
- [Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs](https://mlsanity.com/paper/2502.07942/) (2025)
- [Reinforcement World Model Learning for LLM-based Agents](https://mlsanity.com/paper/2602.05842/) (2026)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [WebGuard: Building a Generalizable Guardrail for Web Agents](https://mlsanity.com/paper/2507.14293/) (2025)
- [Scaling Autonomous Agents via Automatic Reward Modeling And Planning](https://mlsanity.com/paper/2502.12130/) (2025)
- [StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs](https://mlsanity.com/paper/2503.20527/) (2025)
- [Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents](https://mlsanity.com/paper/2506.00320/) (2025)
- [Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification](https://mlsanity.com/paper/2507.11662/) (2025)
- [DynaWeb: Model-Based Reinforcement Learning of Web Agents](https://mlsanity.com/paper/2601.22149/) (2026)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction](https://mlsanity.com/paper/2604.05477/) (2026)
- [Breaking the Data Barrier -- Building GUI Agents Through Task Generalization](https://mlsanity.com/paper/2504.10127/) (2025)
- [AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery](https://mlsanity.com/paper/2505.21499/) (2025)
- [Dyna-Mind: Learning to Simulate from Experience for Better AI Agents](https://mlsanity.com/paper/2510.09577/) (2025)
- [Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling](https://mlsanity.com/paper/2412.14860/) (2024)

## Abstract (arXiv)

Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance, particularly in intricate web environments and long-horizon tasks. To address these limitations, we present ExACT, an approach to combine test-time search and self-learning to build o1-like models for agentic applications. We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore decision space on the fly. R-MCTS extends traditional MCTS by 1) incorporating contrastive reflection, allowing agents to learn from past interactions and dynamically improve their search efficiency; and 2) using multi-agent debate for reliable state evaluation. Next, we introduce Exploratory Learning, a novel learning strategy to teach agents to search at inference time without relying on any external search algorithms. On the challenging VisualWebArena benchmark, our GPT-4o based R-MCTS agent achieves a 6% to 30% relative improvement across various tasks compared to the previous state-of-the-art. Additionally, we show that the knowledge and experience gained from test-time search can be effectively transferred back to GPT-4o via fine-tuning. After Exploratory Learning, GPT-4o 1) demonstrates the ability to explore the environment, evaluate a state, and backtrack to viable ones when it detects that the current state cannot lead to success, and 2) matches 87% of R-MCTS's performance while using significantly less compute. Notably, our work demonstrates the compute scaling properties in both training - data collection with R-MCTS - and testing time. These results suggest a promising research direction to enhance VLMs' capabilities for agentic applications via test-time search and self-learning.